A Hybrid convolution neural network for the classification of tree species using hyperspectral imagery.

In recent years, the advancement of hyperspectral remote sensing technology has greatly enhanced the detailed mapping of tree species. Nevertheless, delving deep into the significance of hyperspectral remote sensing data features for tree species recognition remains a challenging endeavor. The method of Hybrid-CS was proposed to addresses this challenge by synergizing the strengths of both deep learning and traditional learning techniques. Initially, we extract comprehensive correlation structures and spectral features. Subsequently, a hybrid approach, combining correlation-based feature selection with an optimized recursive feature elimination algorithm, identifies the most valuable feature set. We leverage the Support Vector Machine algorithm to evaluate feature importance and perform classification. Through rigorous experimentation, we evaluate the robustness of hyperspectral image-derived features and compare our method with other state-of-the-art classification methods. The results demonstrate: (1) Superior classification accuracy compared to traditional machine learning methods (e.g., SVM, RF) and advanced deep learning approaches on the tree species dataset. (2) Enhanced classification accuracy achieved by incorporating SVM and CNN information, particularly with the integration of attention mechanisms into the network architecture. Additionally, the classification performance of a two-branch network surpasses that of a single-branch network. (3) Consistent high accuracy across different proportions of training samples, indicating the stability and robustness of the method. This study underscores the potential of hyperspectral images and our proposed methodology for achieving precise tree species classification, thus holding significant promise for applications in forest resource management and monitoring.

A Flexible Piezocapacitive Pressure Sensor with Microsphere-Array Electrodes.

Flexible pressure sensors that emulate the sensation and characteristics of natural skins are of great importance in wearable medical devices, intelligent robots, and human-machine interfaces. The microstructure of the pressure-sensitive layer plays a significant role in the sensor's overall performance. However, microstructures usually require complex and costly processes such as photolithography or chemical etching for fabrication. This paper proposes a novel approach that combines self-assembled technology to prepare a high-performance flexible capacitive pressure sensor with a microsphere-array gold electrode and a nanofiber nonwoven dielectric material. When subjected to pressure, the microsphere structures of the gold electrode deform via compressing the medium layer, leading to a significant increase in the relative area between the electrodes and a corresponding change in the thickness of the medium layer, as simulated in COMSOL simulations and experiments, which presents high sensitivity (1.807 kPa-1). The developed sensor demonstrates excellent performance in detecting signals such as slight object deformations and human finger bending.

A study on limited pre-sale strategy with consideration of consumer regret.

The effect of regret on consumers' purchasing behavior is more and more obvious. The limited pre-sale can make retailers with limited production capacity allocate two periods of stock effectively and increase their income. This paper considers the heterogeneous consumers with regret behavior in the market and constructs a model to study the retailer's optimal limited pre-sale strategy. The results show that the high price regret sensitivity negatively affects the higher price of the products in the pre-sale strategy, while the out-of-stock regret sensitivity negatively affects the retailer's profit When the production capacity is relatively low, the proportion of rational consumers is large and the high price regret sensitivity coefficient is small, the retailer should pre-sell at a limited discount and the lowest valuation, and the highest valuation is on sale, otherwise, it should be sold at a price slightly lower than the highest valuation, but when the capacity is very sufficient, the sensitive coefficient of stock-out regret is small and the proportion of rational consumers is small, the retailer should pre-sell at an unlimited premium, and a price slightly lower than the highest valuation of the pre-sale, the lowest valuation of the sale, or should be pre-sold at the highest valuation.

Research on carbon emission reduction and blockchain investment under different dual-channel supply chains.

Based on the consideration that consumers have low-carbon sensitivity and channel preference, a Stackelberg game model dominated by the manufacturer was constructed to study the joint strategies of low-carbon emission reduction and blockchain investment of supply chain members under three models: traditional retailer dual channel, manufacturer's online direct sales dual channel, and third-party e-commerce distribution dual channel. The interaction of different levels of emission reduction and blockchain investment in different dual-channel models was verified through the calculation and simulation analysis of the optimal decision of the supply chain members. The research results showed that the optimal emission reduction of manufacturers and the blockchain investment level of retailers under different dual-channel models are distinguishing, and manufacturers have the highest emission reduction under the dual-channel model of direct online sales; when manufacturers invest the same amount of emission reduction, the traditional retailer dual-channel model can obtain the highest profit. In the process of emission reduction decision-making, there are technology investors and beneficiaries, and the investment level is affected by the dual benefit effect of low-carbon emission reduction and trust and the combined effect of cost input. And the profit of the dual channel of third-party e-commerce distribution is the lowest; the ratio of technology gain to cost investment in the supply chain determines the initiative of low-carbon investment. Meanwhile, there are specific blockchain investment thresholds in different dual-channel modes, and the increase of the threshold value will improve the emission reduction. Besides, emission reduction investment is driven by the manufacturer's profit, and the more the manufacturer's channel accounts for, the higher the emission reduction tends to be. And further from the perspective of profit and emission reduction, it provides a reference for the channel selection and joint emission reduction strategies of the supply chain.

Skin-Attachable Sensors for Biomedical Applications.

With the growing concern about human health issues, especially during the outbreak of the COVID-19 pandemic, the demand for personalized healthcare regarding disease prevention and recovery is increasing. However, tremendous challenges lie in both limited public medical resources and costly medical diagnosis approaches. Recently, skin-attachable sensors have emerged as promising health monitoring platforms to overcome such difficulties. Owing to the advantages of good comfort and high signal-to-noise ratio, skin-attachable sensors enable household, real-time, and long-term detection of weak physiological signals to efficiently and accurately monitor human motion, heart rate, blood oxygen saturation, respiratory rate, lung and heart sound, glucose, and biomarkers in biomedical applications. To further improve the integration level of biomedical skin-attachable sensors, efforts have been made in combining multiple sensing techniques with elaborate structural designs. This review summarizes the recent advances in different functional skin-attachable sensors, which monitor physical and chemical indicators of the human body. The advantages, shortcomings, and integration strategies of different mechanisms are presented. Specially, we highlight sensors monitoring pulmonary function such as respiratory rate and blood oxygen saturation for their potential usage in the COVID-19 pandemic. Finally, the future development of skin-attachable sensors is envisioned.

Enhanced Dielectric Performance of P(VDF-HFP) Composites with Satellite-Core-Structured Fe2O3@BaTiO3 Nanofillers.

Polymer dielectric materials are extensively used in electronic devices. To enhance the dielectric constant, ceramic fillers with high dielectric constant have been widely introduced into polymer matrices. However, to obtain high permittivity, a large added amount (>50 vol%) is usually needed. With the aim of improving dielectric properties with low filler content, satellite-core-structured Fe2O3@BaTiO3 (Fe2O3@BT) nanoparticles were fabricated as fillers for a poly(vinylidene fluoride-co-hexafluoropropylene) (P(VDF-HFP)) matrix. The interfacial polarization effect is increased by Fe2O3 nanoparticles, and thus, composite permittivity is enhanced. Besides, the satellite-core structure prevents Fe2O3 particles from directly contacting each other, so that the dielectric loss remains relatively low. Typically, with 20 vol% Fe2O3@BT nanoparticle fillers, the permittivity of the composite is 31.7 (1 kHz), nearly 1.8 and 3.0 times that of 20 vol% BT composites and pure polymers, respectively. Nanocomposites also achieve high breakdown strength (>150 KV/mm) and low loss tangent (~0.05). Moreover, the composites exhibited excellent flexibility and maintained good dielectric properties after bending. These results demonstrate that composite films possess broad application prospects in flexible electronics.

Research on Key Techniques of Insect Flapping Onset Control Based on Electrical Stimulation.

In this paper, an insect flapping onset control method based on electrical stimulation is proposed. The beetle (Allomyrina dithotomus, Coleoptera) is employed for the research carrier, and it's left and right longitudinal muscles are electrically stimulated to control the flapping onset behavior. The control principle of insect flapping onset utilizing electrical stimulation is analyzed firstly followed by the movement function of the dorsal longitudinal muscle. Subsequently, a micro-control system, which is composed of a PC controller, coordinator and electronic backpack, is designed to realize the wireless control of beetle movements. Finally, the verification experiment is implemented to verify the effectiveness of dorsal longitudinal muscle stimulation with respect to the beetle flapping onset, whereas the comparative experiment emphasizes on determining optimal simulating parameters. The experimental results demonstrate that when the period, duty ratio, number of and amplitude of pulses stimulation signal are assigned to 5 ms, 20%, 90 and 3.3 V respectively, the beetle flapping onset can be controlled with an average response time of 1.69 s. Simultaneously, the optimization of duty ratio from 20% to 40%, and the number of pulses from 90 to 100, is proved to the best parameter configuration.

In-situ preparation of hierarchical flower-like TiO2/carbon nanostructures as fillers for polymer composites with enhanced dielectric properties.

Novel three-dimensional hierarchical flower-like TiO2/carbon (TiO2/C) nanostructures were in-situ synthesized via a solvothermal method involving calcination of organic precursor under inert atmosphere. The composite films comprised of P (VDF-HFP) and as-prepared hierarchical flower-like TiO2/C were fabricated by a solution casting and hot-pressing approach. The results reveal that loading the fillers with a small amount of carbon is an effective way to improve the dielectric constant and suppress the dielectric loss. In addition, TiO2/C particles with higher carbon contents exhibit superiority in promoting the dielectric constants of composites when compared with their noncarbon counterparts. For instance, the highest dielectric constant (330.6) of the TiO2/C composites is 10 times over that of noncarbon-TiO2-filled ones at the same filler volume fraction, and 32 times over that of pristine P (VDF-HFP). The enhancement in the dielectric constant can be attributed to the formation of a large network, which is composed of local micro-capacitors with carbon particles as electrodes and TiO2 as the dielectric in between.